bert_12_layer_model_v1_complete_training_new_emb_compress_48
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.0511
- Accuracy: 0.2770
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
7.113 | 0.08 | 10000 | 7.0896 | 0.0861 |
6.6834 | 0.16 | 20000 | 6.6788 | 0.1081 |
6.5365 | 0.25 | 30000 | 6.5339 | 0.1193 |
6.451 | 0.33 | 40000 | 6.4395 | 0.1270 |
6.3786 | 0.41 | 50000 | 6.3752 | 0.1316 |
6.3313 | 0.49 | 60000 | 6.3221 | 0.1352 |
6.2871 | 0.57 | 70000 | 6.2817 | 0.1380 |
6.2558 | 0.66 | 80000 | 6.2495 | 0.1408 |
6.2231 | 0.74 | 90000 | 6.2207 | 0.1424 |
6.1954 | 0.82 | 100000 | 6.1966 | 0.1438 |
6.1763 | 0.9 | 110000 | 6.1737 | 0.1447 |
6.1531 | 0.98 | 120000 | 6.1465 | 0.1465 |
6.1082 | 1.07 | 130000 | 6.1074 | 0.1482 |
6.0661 | 1.15 | 140000 | 6.0585 | 0.1491 |
5.9843 | 1.23 | 150000 | 5.9751 | 0.1531 |
5.9088 | 1.31 | 160000 | 5.8809 | 0.1686 |
5.771 | 1.39 | 170000 | 5.7305 | 0.1955 |
5.5567 | 1.47 | 180000 | 5.4930 | 0.2282 |
5.3605 | 1.56 | 190000 | 5.2987 | 0.2493 |
5.135 | 1.64 | 200000 | 5.0511 | 0.2770 |
Framework versions
- Transformers 4.30.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.